Method and system for automatic task time estimation and scheduling

Patent metadata

Field	Value
Publication number	US-11803818-B2
Application number	US-202117245044-A
Country	US
Kind code	B2
Filing date	Apr 30, 2021
Priority date	Mar 15, 2013
Publication date	Oct 31, 2023
Grant date	Oct 31, 2023

Abstract

A method and system for automatic task time estimation and scheduling comprising the steps of: (1) storing a plurality of media items; (2) defining an aggregate task; (3) storing participant data and historical time data; (4) determining a plurality of metadata attributes; and (5) determining a final time estimate.

First claim

We claim:

1. A computer-implemented method for automatic task time estimation and scheduling for electronic learning, using a computing device comprising at least one processor and at least one computer-readable storage device, the method comprising the steps of:
storing a plurality of media items on the computer-readable storage device, each media item comprising content information, each media item associated with a media item category, the media item category comprising at least one selected from the group of: an image category, a video category, an audio category, a question category, and a hybrid category;
defining an aggregate task comprising a plurality of component tasks, wherein each task in the plurality of component tasks is defined in relation to at least one corresponding item in the plurality of media items;
storing participant data for at least one participant on the computer-readable storage device;
storing historical time data for the at least one participant on the computer-readable storage device, wherein for each participant in the at least one participant, the historical time data comprises a plurality of historical completion time values stored on the computer-readable storage device, wherein each historical completion time value is stored in relation to a plurality of factors of a media item comprising at least the following: the media item category, a difficulty level, and an average rate per media item(s) per difficulty level of the media item for the each participant in the at least one participant, wherein the average rate per media item per difficulty level is determined using a correction factor based on a network or machine latency for the each participant in the at least one participant;
operating a processor of the computing device to determine a plurality of corresponding metadata attributes for the aggregate task by, for each component task in the aggregate task, determining a media item category for the at least one corresponding item for that component task, and deriving at least one corresponding metadata attribute from the at least one corresponding item for that component task, the at least one corresponding metadata attribute comprising the difficulty level; and
operating the processor to determine a final time estimate for the participant to complete the aggregate task based on at least the plurality of corresponding metadata attributes for that aggregate task, the participant data for the participant, and the historical time data for the participant or other participants in the at least one participant.

2. The method as defined in claim 1 wherein the at least one participant comprises only a single participant, the participant data being a participant profile for that participant, such that operating the processor to determine the final time estimate for completing the aggregate task comprises determining a final time estimate for that single participant to complete the aggregate task.

3. The method as defined in claim 1 further comprising:
for each participant in the at least one participant, the participant data further comprises a plurality of participant-specific time variation factors on the computer-readable storage device comprising at least one of the following: a settling time factor, an idle time factor, a packing-up time factor, and a task-dependent time factor.

4. The method as defined in claim 1 further comprising:
configuring the processor to receive an input value representing a media item category and to derive metadata attributes from the media item based on the input value, wherein:
if the input value indicates that the media item category is video, then the processor is configured to derive the difficulty level and a length variable based on the content information of the video;
if the input value indicates that the media item category is audio, then the processor is configured to derive the difficulty level and a length variable based on the content information of the audio;
if the input value indicates that the media item category is English text, then the processor is configured to derive the difficulty level based on the vocabulary in the text, and a length variable based on the word count of the text, wherein both the vocabulary and the word count are derived from the content information of the English text;
if the input value indicates that the media item category is mathematical text, then the processor is configured to derive the difficulty level based on the mathematical operators in the text, and a length variable based on the word count of the text, wherein both the mathematical operators and the word count are derived from the content information of the mathematical text;
if the input value indicates that the media item category is an English problem set, then the processor is configured to derive the difficulty level based on the vocabulary in the English problem set, and a length variable based on the total number of questions in the English problem set, wherein both the vocabulary and the total number of questions are derived from the content information of the English problem set;
if the input value indicates that the media item category is a mathematical problem set, then the processor is configured to derive the difficulty level based on the mathematical operators in the mathematical problem set, and a length variable based on the total number of questions in the mathematical problem set, wherein both the vocabulary and the total number of questions are derived from the content information of the mathematical problem set; and
if the input value indicates that the media item category is hybrid, then the processor is configured to derive the difficulty level based on user input.

5. The method as defined in claim 1 further comprising:
operating the processor to determine a plurality of component time estimates, wherein each component time estimate in the plurality of the component time estimates is the time estimate for the participant to complete a component task in the aggregate task, each component time estimate being determined based on the media item category, the at least one corresponding metadata attribute for the corresponding component task, the participant data of the participant, and the historical time data of the participant or other participants in the at least one participant; and
operating the processor to determine the final time estimate for the participant to complete the aggregate task based on the sum of the plurality of component time estimates and an additional average total time between the component tasks.

6. The method as defined in claim 5 , wherein operating the processor to determine a component time estimate for the participant to complete a component task in the aggregate task further comprises operating the processor to:
determine the at least one corresponding item based on the component task;
for each corresponding item, determine the length variable, the difficulty level, and the media item category;
for each corresponding item, determine the average rate per media item(s) per difficulty level of the corresponding item based on the historical time data; and
determine the component time estimate by multiplying the length variable of the corresponding item with the average rate per media item(s) per difficulty level of the corresponding item.

7. The method as defined in claim 6 , wherein operating the processor to determine a component time estimate for the participant to complete a component task in the aggregate task further comprises the steps of:
if the processor locates the participant data for the participant in the computer-readable storage device:
if the processor locates the media item category of the at least one corresponding item of the c

Assignees

• D2L Corp

Inventors

• Mullings Owen
• Baker John

Classifications

• G06Q10/1097 Primary

  using calendar-based scheduling for task assignment · CPC title